From your coding agent

Time

2 minutes.

You need

• On your laptop done
• Claude Code, Codex or pi, open in a Git repository of yours

Set this up with your agent

Copy this to a coding agent on your laptop. It runs the commands and checks each step with you; what you sign in to, press or paste stays yours.

This is for a coding agent that can run commands on my laptop (Claude Code, Codex, Cursor), not a chat website.
Walk me through Loopgate's docs page "From your coding agent": https://loopgate.dev/docs/agent.md. The pages it links to are beside it, each ending in .md.
Run its commands yourself, on my laptop or on my box over SSH as the page says, one step at a time, and check each "You should see" line before the next step.
These are mine: tell me when it is my turn, wait for me, and never ask me to type them into this chat. Signing in to anything (the portal, a cloud console, Slack, GitHub), pressing Add a runner, every token and password, my AI subscription's device code, and making the Slack app.
If I paste you the portal's install line, run it on the box: its token works once, for an hour.

Steps

1. Put the loopgate command on your path.

   Copy

   npm install -g loopgate

   You should see: loopgate --version print a version.

2. Install the skill.

   Copy

   loopgate skill install

   You should see: the four folders it wrote, ~/.agents/skills/loopgate first, then the links to it under ~/.claude/skills, ~/.codex/skills and ~/.pi/agent/skills.

3. In your harness, say what you want run, such as run plan-build-review on this, Fable plans and Sol builds. Name models you are signed in to.

   You should see: the workflow drawn in a code block, then the plan: every step's engine, access and pace, the rounds, and the gates you will answer.

4. Say yes.

   You should see: the run's link. It opens the same run in the workbench.

5. Keep working. The agent waits with loopgate wait and relays the ask when the run needs you.

   You should see: the step's reply and the question in your harness, in words.

6. Answer in your own words: an option's number or name (such as Open PR), Continue, Lock, yes or no.

   You should see: the agent run loopgate decide with your words, and the run go on.

Good to know

• Your agent uses six commands: loopgate workflows, plan, run, wait, decide and tell. The commands lists the rest.
• A gate is yours. The agent asks you and passes on your answer; it never answers one itself.
• One task is one run. Parallel work is lanes inside it, never several runs.
• tell carries your words to a step verbatim: a reply while it waits, a steer while it works, a note before it runs.
• loopgate plan … --on <runner> and loopgate run launch.yaml --on <runner> start on your team's runner, in its workspace with the same Git origin.
• Nothing costs a token between those moments. loopgate status <run> and the link show where it is.

If something is off

• Codex cannot reach Loopgate. Its sandbox blocks the daemon's socket. Let it run loopgate escalated, or allow it in ~/.codex/config.toml:

  Copy

  [sandbox_workspace_write]
  network_access = true

• skill install says a different skill exists. Another skill sits in one of the four folders. Move it aside and run it again.

• The plan names another engine than yours. The model you named is not signed in, so a ready one was fitted in its place. Sign in to it, or tell the agent which signed-in model to use.

Next

• The commands
• The patterns